CN110991749A - Heat supply load prediction method and device - Google Patents

Heat supply load prediction method and device Download PDF

Info

Publication number
CN110991749A
CN110991749A CN201911239065.0A CN201911239065A CN110991749A CN 110991749 A CN110991749 A CN 110991749A CN 201911239065 A CN201911239065 A CN 201911239065A CN 110991749 A CN110991749 A CN 110991749A
Authority
CN
China
Prior art keywords
neural network
indoor temperature
heat supply
load prediction
prediction
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201911239065.0A
Other languages
Chinese (zh)
Inventor
刘潇
周丽霞
王婷
袁瑞铭
丁恒春
钟侃
李斯琪
许琦
高帅
高赐威
丁建勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
North China Electric Power Research Institute Co Ltd
Southeast University
Electric Power Research Institute of State Grid Jibei Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
North China Electric Power Research Institute Co Ltd
Southeast University
Electric Power Research Institute of State Grid Jibei Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, North China Electric Power Research Institute Co Ltd, Southeast University, Electric Power Research Institute of State Grid Jibei Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN201911239065.0A priority Critical patent/CN110991749A/en
Publication of CN110991749A publication Critical patent/CN110991749A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The embodiment of the application provides a heat supply load prediction method and a heat supply load prediction device, wherein the method comprises the following steps: determining an indoor temperature prediction range of a target time period according to the current indoor environment parameters and an indoor temperature prediction model; determining the heat supply load prediction range of the target time period according to the indoor temperature prediction range, the outdoor prediction environment parameters of the target time period and the heat supply load prediction model; this application can become the heat supply load interval by traditional load curve under the prerequisite that satisfies human travelling comfort requirement for total heat supply load has elasticity in each period, and then can make thermoelectric unit's peak regulation more accurate nimble.

Description

Heat supply load prediction method and device
Technical Field
The application relates to the field of power systems, in particular to a heat supply load prediction method and a heat supply load prediction device.
Background
Because northern areas are cold in winter, ensuring the heating of residents is an indispensable task every year. At present, a cogeneration unit is mostly adopted for central heating, and most units run in a mode of 'fixing power by heat', so that the peak regulation capacity of a thermal power generating unit is limited in winter, the wind power grid-surfing space is greatly compressed, and the phenomenon of wind abandon is serious. In actual engineering, heat supply companies mostly adopt a heat supply mode higher than the heat load demand of residents, and resource waste is caused.
The inventor finds that in the prior art, for the fine solving of the user side heat load, modeling is mostly adopted for pipelines, houses and the like, and not only the calculation is complex, but also a large number of parameters such as pipelines, house structures and the like are needed, so that the difficulty in actual operation is serious.
Meanwhile, along with the development of the neural network, the application is more and more applied in load prediction, but the traditional neural network method has the defects of low convergence speed and easy falling into local optimization.
Furthermore, at present, researchers mostly study the heat supply problem in the power system in a traditional heat supply load curve mode, the heat supply load in each time period lacks the regulation elasticity, and according to the thermal comfort of the human body, the heat load in the room is reduced in a short time, and the human body does not feel uncomfortable.
Disclosure of Invention
Aiming at the problems in the prior art, the application provides a heat supply load prediction method and a heat supply load prediction device, which can change the heat supply load from a traditional load curve into a heat supply load interval on the premise of meeting the requirement of human body comfort, so that the total heat supply load has elasticity in each time interval, and the peak regulation of a thermoelectric unit can be more accurate and flexible.
In order to solve at least one of the above problems, the present application provides the following technical solutions:
in a first aspect, the present application provides a heating load prediction method, including:
determining an indoor temperature prediction range of a target time period according to the current indoor environment parameters and an indoor temperature prediction model;
and determining the heat supply load prediction range of the target time period according to the indoor temperature prediction range, the outdoor prediction environment parameters of the target time period and the heat supply load prediction model.
Further, after the determining the heating load prediction range of the target period, the method includes:
and carrying out peak regulation on the power grid generator set according to the current power grid heat supply load and the target heat supply load prediction range.
Further, before the determining the indoor temperature prediction range of the target time period according to the current indoor environment parameter and the indoor temperature prediction model, the method includes:
determining the corresponding relation between the preset human body thermal sensation information and the preset user indoor temperature evaluation information in each time period;
and determining the indoor temperature prediction model according to the corresponding relation between the human body thermal sensation information and the user indoor temperature evaluation information in each time period.
Further, the determining an indoor temperature prediction range of a target time period according to the current indoor environment parameter and the indoor temperature prediction model includes:
and determining the indoor temperature prediction range of the target time period according to the indoor temperature prediction model and the current indoor environment parameters corresponding to the target time period.
Further, before determining the heat supply load prediction range of the target time interval according to the indoor temperature prediction range, the outdoor prediction environment parameter of the target time interval and the heat supply load prediction model, the method includes:
collecting sample data;
determining a neural network input layer of the heat supply load prediction model according to outdoor temperature data, outdoor wind speed data, outdoor wind direction data, outdoor air humidity data and indoor temperature data in the sample data;
setting heat supply load data as a neural network output layer of the heat supply load prediction model;
and determining the neural network of the heat supply load prediction model according to the neural network input layer, the neural network output layer and the hidden layers with preset number.
Further, after the determining the neural network structure of the heating load prediction model, the method includes:
initializing the neural network;
performing iterative optimization on the neural network according to a preset particle swarm optimization model to obtain an optimal neural network;
setting the space vector in the particle swarm optimization model as a weight and a threshold value in the optimal neural network, and training the optimal neural network to obtain the trained neural network.
Further, before the iterative optimization of the neural network according to the preset particle swarm optimization model to obtain an optimal neural network, the method includes:
initializing characteristic parameters of the particle swarm optimization model;
and performing population replication and/or population crossing and/or population variation treatment on each particle population in the particle swarm optimization model according to a preset genetic model, and updating the particle swarm optimization model until the particle swarm optimization model meets a preset iteration termination condition.
In a second aspect, the present application provides a heating load prediction apparatus, comprising:
the indoor temperature range prediction module is used for determining an indoor temperature prediction range of a target time period according to the current indoor environment parameters and the indoor temperature prediction model;
and the heat supply load range prediction module is used for determining the heat supply load prediction range of the target time period according to the indoor temperature prediction range, the outdoor prediction environment parameters of the target time period and the heat supply load prediction model.
Further, still include:
and the dynamic peak regulation unit is used for carrying out peak regulation on the power grid generator set according to the current power grid heat supply load and the target heat supply load prediction range.
Further, still include:
the heat feeling corresponding relation determining unit is used for determining the corresponding relation between preset human body heat feeling information and preset user indoor temperature evaluation information in each time period;
and the indoor temperature prediction model determining unit is used for determining the indoor temperature prediction model according to the corresponding relation between the human body thermal feeling information and the user indoor temperature evaluation information in each time period.
Further, the indoor temperature range prediction module includes:
and the indoor temperature prediction range determining unit is used for determining the indoor temperature prediction range of the target time period according to the indoor temperature prediction model and the current indoor environment parameter corresponding to the target time period.
Further, still include:
the sample data acquisition unit is used for acquiring sample data;
the neural network input layer determining unit is used for determining the neural network input layer of the heat supply load prediction model according to the outdoor temperature data, the outdoor wind speed data, the outdoor wind direction data, the outdoor air humidity data and the indoor temperature data in the sample data;
a neural network output layer determining unit for setting the heat supply load data as a neural network output layer of the heat supply load prediction model;
and the neural network construction unit is used for determining the neural network of the heat supply load prediction model according to the neural network input layer, the neural network output layer and a preset number of hidden layers.
Further, still include:
the neural network training preprocessing unit is used for initializing the neural network;
the neural network optimization unit is used for performing iterative optimization on the neural network according to a preset particle swarm optimization model to obtain an optimal neural network;
and the neural network training unit is used for setting the space vector in the particle swarm optimization model as the weight and the threshold value in the optimal neural network, and training the optimal neural network to obtain the trained neural network.
Further, still include:
the particle swarm optimization model preprocessing unit is used for initializing the characteristic parameters of the particle swarm optimization model;
and the particle swarm optimization model optimization unit is used for performing population replication and/or population crossing and/or population variation treatment on each particle population in the particle swarm optimization model according to a preset genetic model, and updating the particle swarm optimization model until the particle swarm optimization model meets a preset iteration termination condition.
In a third aspect, the present application provides an electronic device, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the heating load prediction method when executing the program.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the heating load prediction method.
According to the technical scheme, the indoor temperature prediction range of the target time interval is determined according to the current indoor environment parameter and the indoor temperature prediction model so as to meet the requirement of comfort of a human body on temperature, and then the heat supply load prediction range of the target time interval is determined according to the indoor temperature prediction range, the outdoor prediction environment parameter of the target time interval and the heat supply load prediction model.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a heating load prediction method in an embodiment of the present application;
FIG. 2 is a second flowchart of a heating load prediction method according to an embodiment of the present application;
fig. 3 is a third schematic flow chart of a heating load prediction method in the embodiment of the present application;
FIG. 4 is a fourth flowchart illustrating a heating load prediction method according to an embodiment of the present application;
fig. 5 is a fifth flowchart illustrating a heating load prediction method according to an embodiment of the present application;
fig. 6 is one of the structural diagrams of the heating load prediction apparatus in the embodiment of the present application;
fig. 7 is a second block diagram of a heating load prediction apparatus according to an embodiment of the present invention;
fig. 8 is a third structural view of a heating load prediction apparatus in the embodiment of the present application;
fig. 9 is a fourth configuration diagram of the heating load prediction apparatus in the embodiment of the present application;
fig. 10 is a fifth configuration diagram of a heating load prediction apparatus in the embodiment of the present application;
fig. 11 is a sixth configuration diagram of a heating load prediction apparatus in the embodiment of the present application;
FIG. 12 is a diagram of a neural network structure of a heating load prediction model according to an embodiment of the present application;
FIG. 13 is a diagram illustrating a corresponding relationship between PMV and PPD in the embodiment of the present application;
fig. 14 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Considering that in the prior art, a modeling mode for pipelines, houses and the like is mostly adopted for the refined solution of user side heat loads, not only the calculation is complex, but also a large number of parameters such as pipelines, house structures and the like are needed, so that the problem of difficulty and heaviness in actual operation is solved, meanwhile, along with the development of a neural network, the application is more and more applied in load prediction, but the problem that the traditional neural network method is slow in convergence speed and easy to fall into local optimum exists, and the problem that a scholars mostly studies in a traditional heat supply load curve mode when studying heat supply problems in a power system at present, the heat supply load at each time period lacks regulation elasticity, and according to the thermal comfort of human bodies, the heat load is reduced in a short time, and the human bodies cannot feel uncomfortable is solved, the method comprises the steps of determining an indoor temperature prediction range of a target time period to meet the requirement of a human body on the comfort of the temperature, and then determining a heat supply load prediction range of the target time period according to the indoor temperature prediction range, outdoor prediction environment parameters of the target time period and a heat supply load prediction model.
In order to change a heat supply load from a traditional load curve into a heat supply load interval on the premise of meeting the requirement of human comfort, so that the total heat supply load has elasticity in each time interval and the peak shaving of the thermoelectric unit is more accurate and flexible, the application provides an embodiment of a heat supply load prediction method, and referring to fig. 1, the heat supply load prediction method specifically comprises the following contents:
step S101: and determining the indoor temperature prediction range of the target time period according to the current indoor environment parameters and the indoor temperature prediction model.
It is understood that the current indoor environmental parameters include, but are not limited to: the indoor temperature, the indoor air humidity and the indoor air pressure can be determined through a preset indoor temperature prediction model, wherein the indoor temperature prediction range is a range of comfortable air temperature when a human body is in the room in the target time period, for example, in the time period from 6 ℃ early to 7 ℃ early, the indoor temperature prediction range is 23-24 ℃, namely, if the indoor temperature is 23-24 ℃, the thermal sensation of the human body belongs to a comfortable state, and for example, in the time period from 12 pm to 14 pm, the indoor temperature prediction range is 20-23 ℃, namely, if the indoor temperature is 20-23 ℃, the thermal sensation of the human body belongs to a comfortable state.
Step S102: and determining the heat supply load prediction range of the target time period according to the indoor temperature prediction range, the outdoor prediction environment parameters of the target time period and the heat supply load prediction model.
It can be understood that, by combining the indoor temperature prediction range and the outdoor prediction environment parameter of the target time interval, the heating load prediction range required to be provided by the power grid in the target time interval is determined through a preset heating load prediction model, wherein the outdoor prediction environment parameter includes but is not limited to: temperature, humidity, wind speed and wind direction parameters.
It is understood that the heating load prediction model may be any model capable of performing prediction based on a neural network, and since input data and output data of the model during prediction are both derived from an actual production environment, a prediction behavior of the model is closely fitted with the actual production environment and conforms to a natural rule.
As can be seen from the above description, the heat supply load prediction method provided in the embodiment of the present application can determine the indoor temperature prediction range of the target time interval according to the current indoor environment parameter and the indoor temperature prediction model to meet the comfort requirement of the human body on the temperature, and then determine the heat supply load prediction range of the target time interval according to the indoor temperature prediction range, the outdoor prediction environment parameter of the target time interval, and the heat supply load prediction model.
In order to flexibly and accurately perform peak shaving on the power supply unit so as to improve the power utilization efficiency and save energy, an embodiment of the heat supply load prediction method further specifically includes the following steps:
and carrying out peak regulation on the power grid generator set according to the current power grid heat supply load and the target heat supply load prediction range.
Optionally, according to a difference value between the current power grid heat supply load and the target heat supply load prediction range, a dynamic peak regulation strategy of a generator set (a thermal power generating set or a wind power generating set) in the power grid can be determined through the prior art, so that the resource utilization rate of the whole power system is improved, and the beneficial technical effects of saving energy, reducing the wind abandoning rate and the like are achieved.
In order to construct an indoor temperature prediction model so that the prediction range of the subsequent power supply load can satisfy the thermal comfort of the human body, in an embodiment of the heat supply load prediction method of the present application, referring to fig. 2, the following contents are further specifically included:
step S201: and determining the corresponding relation between the preset human body thermal sensation information and the preset user indoor temperature evaluation information in each time period.
Step S202: and determining the indoor temperature prediction model according to the corresponding relation between the human body thermal sensation information and the user indoor temperature evaluation information in each time period.
First, it is understood that, in the prior art, PMV (Predicted mean volume) (i.e. the preset human body thermal response evaluation index) can be classified into seven levels in table 1 according to the human body thermal sensation, wherein the state of PMV being 0 is the most ideal thermal comfort environment.
TABLE 1PMV index
Figure BDA0002305687780000071
According to the ISO07730 standard, the calculation formula of the available PMV index is as follows:
Figure BDA0002305687780000081
wherein M is human body metabolism rate, wherein when a person sits still, the human body metabolism rate M is a reference value of 1Met (58.2W/M)2) When a person lies flat, M is 0.7Met, and when a person walks, M is 2.0 Met; w is the power of human body; paIs the water vapor partial pressure in ambient air; t is taIs the air temperature; f. ofclThe ratio of the surface area of the dressed human body to the surface area of the naked body; t is tclThe average temperature of the outer surface of the dressed human body;
Figure BDA0002305687780000082
is the average radiant temperature; h iscIs the convective heat transfer coefficient.
Wherein the content of the first and second substances,
Figure BDA0002305687780000083
in the formula (I), the compound is shown in the specification,
Figure BDA0002305687780000084
is the relative humidity of the indoor environment.
Figure BDA0002305687780000085
In the formula IclIs thermal resistance of clothes.
Figure BDA0002305687780000086
Wherein the content of the first and second substances,
Figure BDA0002305687780000087
Figure BDA0002305687780000088
where v is the indoor air flow rate.
The PMV value describes the user's feeling of heat supply, while PPD (predicted dissatisfaction) (i.e. the preset user indoor temperature evaluation information) can describe the user's dissatisfaction degree of heat supply, which is the final index for evaluating heat supply comfort degree, and the index can be directly derived from PMV, and the specific calculation formula is as follows:
PPD＝100-95exp(-0.03353×PMV4-0.2179×PMV2)；
the relationship between PPD and PMV is shown in fig. 13, where PMV is 0, i.e. the most comfortable heat supply, the user dissatisfaction is the lowest, and the dissatisfaction sharply increases as the PMV approaches the extreme values toward both ends.
It is understood that the PPD and PMV correspondence may be set as the indoor temperature prediction model.
In order to determine an indoor temperature prediction range satisfying the thermal comfort of the human body by using the constructed indoor temperature prediction model, in an embodiment of the heat supply load prediction method of the present application, the following contents are further specifically included:
and determining the indoor temperature prediction range of the target time period according to the indoor temperature prediction model and the current indoor environment parameters corresponding to the target time period.
Optionally, as can be seen from the PMV index calculation formula in the previous step, the PMV index is mainly related to parameters such as human metabolic rate, humidity, radiation temperature, convective heat transfer coefficient and the like, and except for the human metabolic rate, other parameters have small change amplitude within one day and are mainly related to the human metabolic rate. Therefore, the living habits of residents need to be researched, and the habits of the residents in different times are divided.
Then, optionally, the user satisfaction is generally controlled to be PPD < 10%, and at this time, the PMV index range is mostly [ -0.5, 0.5], and at this time, the indoor temperature prediction range meeting the thermal comfort PMV requirement can be obtained according to the indoor environment parameters (all having reference values).
In order to construct a neural network suitable for a power supply load prediction model of a thermal power grid, in an embodiment of the heat supply load prediction method of the present application, referring to fig. 3, the following contents are further specifically included:
step S301: and collecting sample data.
Step S302: and determining a neural network input layer of the heat supply load prediction model according to the outdoor temperature data, the outdoor wind speed data, the outdoor wind direction data, the outdoor air humidity data and the indoor temperature data in the sample data.
Step S303: and setting the heat supply load data as a neural network output layer of the heat supply load prediction model.
Step S304: and determining the neural network of the heat supply load prediction model according to the neural network input layer, the neural network output layer and the hidden layers with preset number.
Optionally, first, sample data is collected, specifically, by collecting outdoor wind speed, wind direction, outdoor air humidity, outdoor temperature, indoor temperature of multiple days at different time periods and total heating load of a cell at a corresponding time as sample data, the original data takes one value every 15min, and 96 values are taken in total every day.
Optionally, for convenience of data processing, the wind direction is digitally represented, and the eight wind directions are digitally calibrated in the same time by taking the north direction as a reference, namely, north wind-1, northeast wind-2, east wind-3, southeast wind-4, south wind-5, southwest wind-6, west wind-7 and northwest wind-8.
Optionally, because the refined control of each house cannot be achieved at the current heating user side, in order to guarantee the overall heating effect, it is required to guarantee that the room with the lowest temperature meets the heating requirement, that is, the room with the lowest temperature is selected as the indoor temperature acquisition experiment room. For the heat supply district, a back shadow at the tail end of the heat supply pipe network or a back shadow room at the bottom layer is selected for room temperature measurement, and the measuring points can be distributed at the indoor central position.
Optionally, the core of the application is to establish the relationship between outdoor temperature, outdoor wind speed and direction, outdoor air humidity, indoor temperature and total heating load, i.e.
Figure BDA0002305687780000101
In the formula, Tout(t) is the outdoor temperature at time t; vwind(t) outdoor wind speed at time t; dwind(t) outdoor wind direction at time t;
Figure BDA0002305687780000102
outdoor humidity at time t; t isin(t) is the indoor temperature at time t; q (t) is the total heating load at time t.
Thus, referring to fig. 12, the present application provides a neural network model that builds a three-layer structure:
an input layer: inputting variables related to the total heat load to be predicted, wherein the variables are outdoor temperature, outdoor wind speed, outdoor wind direction, outdoor air humidity and indoor temperature, and the number of nodes is 5;
an output layer: the total heat supply load is taken as output, and the number of the nodes is 1;
hiding the layer: the formula for selecting the number of hidden layer neurons in the application is as follows:
Figure BDA0002305687780000103
wherein n is the number of neurons in the input layer; m is the number of neuron output layers; a is a constant between [1, 10 ]. A is [4, 13], and the excessive number of hidden layer neurons can increase the network calculation amount and easily generate the overfitting problem; if the number of the neurons is too small, the network performance is affected, and the expected effect cannot be achieved, and the number of the hidden layer neurons is selected to be 7 based on the method.
In order to optimize the neural network of the power supply load prediction model for the thermal power grid by using the preset particle swarm optimization model, in an embodiment of the heat supply load prediction method of the present application, referring to fig. 4, the following contents are further specifically included:
step S401: initializing the neural network.
Step S402: and performing iterative optimization on the neural network according to a preset particle swarm optimization model to obtain an optimal neural network.
Step S403: setting the space vector in the particle swarm optimization model as a weight and a threshold value in the optimal neural network, and training the optimal neural network to obtain the trained neural network.
Optionally, first, the neural network structure is initialized, and at the same time, the sample data may be normalized.
Then, initializing each population in the particle swarm optimization model, representing all weights and thresholds in the BP neural network structure by using d-dimensional space vectors in the PSO algorithm, and encoding the weights and the thresholds.
And then, carrying out iterative operation, and carrying out iterative calculation by using the improved preset particle swarm optimization model to obtain a globally optimal individual, namely the optimal structure parameter of the network.
Then, training the neural network, specifically, substituting the initial weight and the threshold obtained by decoding into the neural network structure, and then training the neural network.
In order to optimize the particle swarm optimization model by using the genetic model, in an embodiment of the heat supply load prediction method of the present application, referring to fig. 5, the following contents are further specifically included:
step S501: initializing characteristic parameters of the particle swarm optimization model.
Step S502: and performing population replication and/or population crossing and/or population variation treatment on each particle population in the particle swarm optimization model according to a preset genetic model, and updating the particle swarm optimization model until the particle swarm optimization model meets a preset iteration termination condition.
Optionally, first, characteristic parameters of the particle swarm optimization model are initialized, specifically, the characteristic parameters include but are not limited to: the number of population particles, the maximum iteration number, other parameters required by the particle swarm optimization model in the running calculation process and the like.
Then, a particle swarm optimization is performed, specifically, assuming one is inThe d-dimension target search space has S particles, and the position of the S particle is represented as Xs＝(xs1,xs2,…,xsd) The velocity is represented as Vs＝(vs1,vs2,…,vsd) The update formula of the speed and the position of each iteration is as follows:
Figure BDA0002305687780000111
Figure BDA0002305687780000112
in the formula, Ps＝(ps1,ps2,…,psd) The current optimal position of the s particle is obtained; pg＝(pg1,pg2,…,pgd) The current optimal position of the whole particle swarm is obtained;
Figure BDA0002305687780000113
and
Figure BDA0002305687780000114
respectively the speed and position of the s-th particle at the t-th iteration; c. C1、c2Is a learning factor for the particle; r is1、r2Is [0,1]]A random number in between; and omega is an inertia weight, the larger the value of omega is, the stronger the global optimizing capability is, but the weaker the local optimizing capability is.
And then, evaluating the particles, specifically, calculating the fitness value of the particles after each iteration according to a fitness function formula, and evaluating the particles.
Specifically, the present application uses the mean square error as a fitness function formula:
Figure BDA0002305687780000121
in the formula, n is the number of output nodes; y iskAnd OkRespectively, the desired output and the actual output value of the kth output node.
Then, the population is sorted, specifically, the updated population is sorted according to the sequence of fitness from big to small, and the sorted population is averagely divided into A1And A2Two sub-populations.
Optionally, cross mutation operation can be performed on the sorted population, specifically, if the sub-population A is sorted1The fitness is good, and the data are directly copied to enter the next generation; pair sub-population A2The particles in (1) are subjected to crossover and mutation operations.
Specifically, the method for intersecting the velocity and position of the g-th particle and the h-th particle is as follows:
Figure BDA0002305687780000122
wherein a and b are random numbers between [0,1 ].
The method for carrying out variation on the speed and the position of the r-th particle comprises the following steps:
Figure BDA0002305687780000123
fv(g)＝e2(1-g/Gmax)2，
Figure BDA0002305687780000124
fx(g)＝e4(1-g/Gmax)2，
in the formula (I), the compound is shown in the specification,
Figure BDA0002305687780000125
and
Figure BDA0002305687780000126
respectively representing the upper bound and the lower bound of the speed of the ith particle in the t iteration;
Figure BDA0002305687780000127
and
Figure BDA0002305687780000128
respectively representing the upper and lower bounds of the position of the ith particle at the tth iteration; e.g. of the type1、e2、e3And e4Are all [0,1]A random number in between; g is the current iteration number; gmaxIs the maximum number of iterations.
And then updating the individual extremum and the global extremum, specifically, updating the individual extremum and the global extremum by comparing the calculated fitness value of the current fitness of each particle with the individual extremum and the fitness value of the individual extremum and the particle swarm global extremum.
Finally, iterative optimization is performed, namely the steps are continuously performed until a stop iteration condition is reached (for example, convergence precision is reached or the iteration number is maximized).
In order to change the heat supply load from a traditional load curve into a heat supply load interval on the premise of meeting the requirement of human comfort, so that the total heat supply load has elasticity in each time interval and the peak shaving of the thermoelectric unit is more accurate and flexible, the application provides an embodiment of a heat supply load prediction device for realizing all or part of the heat supply load prediction method, and the heat supply load prediction device specifically comprises the following contents, referring to fig. 6:
an indoor temperature range prediction module 10, configured to determine an indoor temperature prediction range of a target time period according to a current indoor environment parameter and an indoor temperature prediction model;
and the heat supply load range prediction module 20 is configured to determine the heat supply load prediction range in the target time period according to the indoor temperature prediction range, the outdoor prediction environment parameter in the target time period, and the heat supply load prediction model.
As can be seen from the above description, the heat supply load prediction apparatus provided in the embodiment of the present application can determine the indoor temperature prediction range of the target time interval according to the current indoor environment parameter and the indoor temperature prediction model to meet the comfort requirement of the human body on the temperature, and then determine the heat supply load prediction range of the target time interval according to the indoor temperature prediction range, the outdoor prediction environment parameter of the target time interval, and the heat supply load prediction model.
In order to flexibly and accurately peak-load the power supply unit to improve the power utilization efficiency and save energy, an embodiment of the heat supply load prediction apparatus further includes:
and the dynamic peak regulation unit is used for carrying out peak regulation on the power grid generator set according to the current power grid heat supply load and the target heat supply load prediction range.
In order to construct an indoor temperature prediction model so that the prediction range of the subsequent power supply load can satisfy the thermal comfort of the human body, in an embodiment of the heat supply load prediction apparatus of the present application, referring to fig. 7, the method further includes:
the heat sensation corresponding relation determining unit 31 is configured to determine a corresponding relation between preset human heat sensation information and preset user indoor temperature evaluation information in each time period.
An indoor temperature prediction model determining unit 32, configured to determine the indoor temperature prediction model according to a correspondence between the human thermal sensation information and the user indoor temperature evaluation information in each time period.
In order to determine an indoor temperature prediction range satisfying the thermal comfort of the human body by using the constructed indoor temperature prediction model, in an embodiment of the heating load prediction apparatus of the present application, referring to fig. 8, the indoor temperature range prediction module 10 includes:
and an indoor temperature prediction range determining unit 11, configured to determine an indoor temperature prediction range of the target time period according to the indoor temperature prediction model and the current indoor environment parameter corresponding to the target time period.
In order to construct a neural network suitable for a power supply load prediction model of a thermal power grid, in an embodiment of the heat supply load prediction apparatus of the present application, referring to fig. 9, the apparatus further includes:
and a sample data acquisition unit 41, configured to acquire sample data.
And a neural network input layer determining unit 42, configured to determine a neural network input layer of the heat supply load prediction model according to the outdoor temperature data, the outdoor wind speed data, the outdoor wind direction data, the outdoor air humidity data, and the indoor temperature data in the sample data.
A neural network output layer determining unit 43, configured to set the heating load data as a neural network output layer of the heating load prediction model.
And the neural network construction unit 44 is configured to determine a neural network of the heat supply load prediction model according to the neural network input layer, the neural network output layer and a preset number of hidden layers.
In order to optimize the neural network of the power supply load prediction model for the thermal power grid by using the preset particle swarm optimization model, in an embodiment of the heat supply load prediction device of the present application, referring to fig. 10, the device further includes:
a neural network training preprocessing unit 51 for initializing the neural network.
And the neural network optimization unit 52 is configured to perform iterative optimization on the neural network according to a preset particle swarm optimization model to obtain an optimal neural network.
And the neural network training unit 53 is configured to set the space vector in the particle swarm optimization model as a weight and a threshold in the optimal neural network, and train the optimal neural network to obtain a trained neural network.
In order to optimize the particle swarm optimization model by using the genetic model, in an embodiment of the heating load prediction apparatus of the present application, referring to fig. 11, the method further includes:
and the particle swarm optimization model preprocessing unit 61 is used for initializing the characteristic parameters of the particle swarm optimization model.
And the particle swarm optimization model optimization unit 62 is configured to perform population replication and/or population crossing and/or population variation processing on each particle population in the particle swarm optimization model according to a preset genetic model, and update the particle swarm optimization model until the particle swarm optimization model meets a preset iteration termination condition.
An embodiment of the present application further provides a specific implementation manner of an electronic device, which is capable of implementing all steps in the heating load prediction method in the foregoing embodiment, and referring to fig. 14, the electronic device specifically includes the following contents:
a processor (processor)601, a memory (memory)602, a communication interface (communications interface)603, and a bus 604;
the processor 601, the memory 602 and the communication interface 603 complete mutual communication through the bus 604; the communication interface 603 is used for realizing information transmission among a heat supply load prediction device, an online service system, client equipment and other participating mechanisms;
the processor 601 is configured to call a computer program in the memory 602, and the processor executes the computer program to implement all the steps in the heating load prediction method in the above embodiment, for example, when the processor executes the computer program to implement the following steps:
step S101: and determining the indoor temperature prediction range of the target time period according to the current indoor environment parameters and the indoor temperature prediction model.
Step S102: and determining the heat supply load prediction range of the target time period according to the indoor temperature prediction range, the outdoor prediction environment parameters of the target time period and the heat supply load prediction model.
As can be seen from the above description, according to the electronic device provided in the embodiment of the present application, the indoor temperature prediction range of the target time interval can be determined according to the current indoor environment parameter and the indoor temperature prediction model to meet the comfort requirement of the human body on the temperature, and then the heat supply load prediction range of the target time interval is determined according to the indoor temperature prediction range, the outdoor prediction environment parameter of the target time interval, and the heat supply load prediction model.
An embodiment of the present application further provides a computer-readable storage medium capable of implementing all the steps in the heating load prediction method in the above embodiment, where the computer-readable storage medium stores thereon a computer program, and when the computer program is executed by a processor, the computer program implements all the steps in the heating load prediction method in the above embodiment, for example, when the processor executes the computer program, the processor implements the following steps:
step S101: and determining the indoor temperature prediction range of the target time period according to the current indoor environment parameters and the indoor temperature prediction model.
Step S102: and determining the heat supply load prediction range of the target time period according to the indoor temperature prediction range, the outdoor prediction environment parameters of the target time period and the heat supply load prediction model.
As can be seen from the above description, the computer-readable storage medium provided in the embodiment of the present application can determine the indoor temperature prediction range of the target time interval according to the current indoor environment parameter and the indoor temperature prediction model to meet the comfort requirement of the human body on the temperature, and then determine the heat supply load prediction range of the target time interval according to the indoor temperature prediction range, the outdoor prediction environment parameter of the target time interval, and the heat supply load prediction model.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Although the present application provides method steps as described in an embodiment or flowchart, additional or fewer steps may be included based on conventional or non-inventive efforts. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual apparatus or client product executes, it may execute sequentially or in parallel (e.g., in the context of parallel processors or multi-threaded processing) according to the embodiments or methods shown in the figures.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a vehicle-mounted human-computer interaction device, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
The embodiments of this specification may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The described embodiments may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment. In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of an embodiment of the specification. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and variations to the embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present specification should be included in the scope of the claims of the embodiments of the present specification.

Claims (16)

1. A heating load prediction method, characterized in that the method comprises:
determining an indoor temperature prediction range of a target time period according to the current indoor environment parameters and an indoor temperature prediction model;
and determining the heat supply load prediction range of the target time period according to the indoor temperature prediction range, the outdoor prediction environment parameters of the target time period and the heat supply load prediction model.
2. A heating load prediction method according to claim 1, characterized by, after said determining the heating load prediction range for the target period, comprising:
and carrying out peak regulation on the power grid generator set according to the current power grid heat supply load and the target heat supply load prediction range.
3. A heating load prediction method according to claim 1, characterized in that, before determining the indoor temperature prediction range for the target period based on the current indoor environment parameter and the indoor temperature prediction model, it comprises:
determining the corresponding relation between the preset human body thermal sensation information and the preset user indoor temperature evaluation information in each time period;
and determining the indoor temperature prediction model according to the corresponding relation between the human body thermal sensation information and the user indoor temperature evaluation information in each time period.
4. A heating load prediction method according to claim 1, wherein the determining an indoor temperature prediction range for a target time period based on the current indoor environment parameter and an indoor temperature prediction model comprises:
and determining the indoor temperature prediction range of the target time period according to the indoor temperature prediction model and the current indoor environment parameters corresponding to the target time period.
5. A heating load prediction method according to claim 1, before determining the heating load prediction range for the target time period based on the indoor temperature prediction range, the outdoor prediction environmental parameter for the target time period, and the heating load prediction model, comprising:
collecting sample data;
determining a neural network input layer of the heat supply load prediction model according to outdoor temperature data, outdoor wind speed data, outdoor wind direction data, outdoor air humidity data and indoor temperature data in the sample data;
setting heat supply load data as a neural network output layer of the heat supply load prediction model;
and determining the neural network of the heat supply load prediction model according to the neural network input layer, the neural network output layer and the hidden layers with preset number.
6. A heating load prediction method according to claim 5, characterized in that after said determining the neural network structure of the heating load prediction model, it comprises:
initializing the neural network;
performing iterative optimization on the neural network according to a preset particle swarm optimization model to obtain an optimal neural network;
setting the space vector in the particle swarm optimization model as a weight and a threshold value in the optimal neural network, and training the optimal neural network to obtain the trained neural network.
7. The heating load prediction method according to claim 6, wherein before the iterative optimization of the neural network according to the preset particle swarm optimization model to obtain an optimal neural network, the method comprises:
initializing characteristic parameters of the particle swarm optimization model;
and performing population replication and/or population crossing and/or population variation treatment on each particle population in the particle swarm optimization model according to a preset genetic model, and updating the particle swarm optimization model until the particle swarm optimization model meets a preset iteration termination condition.
8. A heating load prediction apparatus, characterized by comprising:
the indoor temperature range prediction module is used for determining an indoor temperature prediction range of a target time period according to the current indoor environment parameters and the indoor temperature prediction model;
and the heat supply load range prediction module is used for determining the heat supply load prediction range of the target time period according to the indoor temperature prediction range, the outdoor prediction environment parameters of the target time period and the heat supply load prediction model.
9. A heating load prediction device as claimed in claim 8, further comprising:
and the dynamic peak regulation unit is used for carrying out peak regulation on the power grid generator set according to the current power grid heat supply load and the target heat supply load prediction range.
10. A heating load prediction device as claimed in claim 8, further comprising:
the heat feeling corresponding relation determining unit is used for determining the corresponding relation between preset human body heat feeling information and preset user indoor temperature evaluation information in each time period;
and the indoor temperature prediction model determining unit is used for determining the indoor temperature prediction model according to the corresponding relation between the human body thermal feeling information and the user indoor temperature evaluation information in each time period.
11. A heating load prediction apparatus as defined in claim 8, wherein the indoor temperature range prediction module comprises:
and the indoor temperature prediction range determining unit is used for determining the indoor temperature prediction range of the target time period according to the indoor temperature prediction model and the current indoor environment parameter corresponding to the target time period.
12. A heating load prediction device as claimed in claim 8, further comprising:
the sample data acquisition unit is used for acquiring sample data;
the neural network input layer determining unit is used for determining the neural network input layer of the heat supply load prediction model according to the outdoor temperature data, the outdoor wind speed data, the outdoor wind direction data, the outdoor air humidity data and the indoor temperature data in the sample data;
a neural network output layer determining unit for setting the heat supply load data as a neural network output layer of the heat supply load prediction model;
and the neural network construction unit is used for determining the neural network of the heat supply load prediction model according to the neural network input layer, the neural network output layer and a preset number of hidden layers.
13. A heating load prediction device as claimed in claim 12, further comprising:
the neural network training preprocessing unit is used for initializing the neural network;
the neural network optimization unit is used for performing iterative optimization on the neural network according to a preset particle swarm optimization model to obtain an optimal neural network;
and the neural network training unit is used for setting the space vector in the particle swarm optimization model as the weight and the threshold value in the optimal neural network, and training the optimal neural network to obtain the trained neural network.
14. A heating load prediction device as claimed in claim 13, further comprising:
the particle swarm optimization model preprocessing unit is used for initializing the characteristic parameters of the particle swarm optimization model;
and the particle swarm optimization model optimization unit is used for performing population replication and/or population crossing and/or population variation treatment on each particle population in the particle swarm optimization model according to a preset genetic model, and updating the particle swarm optimization model until the particle swarm optimization model meets a preset iteration termination condition.
15. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the heating load prediction method according to any one of claims 1 to 7.
16. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the heating load prediction method according to any one of claims 1 to 7.
CN201911239065.0A 2019-12-06 2019-12-06 Heat supply load prediction method and device Pending CN110991749A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911239065.0A CN110991749A (en) 2019-12-06 2019-12-06 Heat supply load prediction method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911239065.0A CN110991749A (en) 2019-12-06 2019-12-06 Heat supply load prediction method and device

Publications (1)

Publication Number Publication Date
CN110991749A true CN110991749A (en) 2020-04-10

Family

ID=70090676

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911239065.0A Pending CN110991749A (en) 2019-12-06 2019-12-06 Heat supply load prediction method and device

Country Status (1)

Country Link
CN (1) CN110991749A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112083746A (en) * 2020-09-25 2020-12-15 陕西科技大学 Intelligent power grid system
CN117040029A (en) * 2023-10-08 2023-11-10 南方电网数字电网研究院有限公司 Power distribution network power dispatching method, device, computer equipment and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102052739A (en) * 2010-12-27 2011-05-11 重庆大学 Central air conditioner intelligent control system based on wireless sensor network and method
CN105656064A (en) * 2015-12-31 2016-06-08 东北电力大学 Method for enabling thermoelectric unit to participate in system peak-load regulation scheduling by using heat supply time lag
CN105805822A (en) * 2016-03-24 2016-07-27 常州英集动力科技有限公司 Heat supply energy saving control method and system based on neural network prediction
CN105913151A (en) * 2016-04-12 2016-08-31 河海大学常州校区 Photovoltaic power station power generation amount predication method based on adaptive mutation particle swarm and BP network
CN107120721A (en) * 2017-05-25 2017-09-01 河北健特建筑安装工程有限公司 A kind of central heating dynamic gas candidate compensation method
CN107704875A (en) * 2017-09-30 2018-02-16 山东建筑大学 Based on the building load Forecasting Methodology and device for improving IHCMAC neutral nets
CN109253494A (en) * 2018-09-05 2019-01-22 东北大学 A kind of electric heat-storage device control system and method based on heat load prediction

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102052739A (en) * 2010-12-27 2011-05-11 重庆大学 Central air conditioner intelligent control system based on wireless sensor network and method
CN105656064A (en) * 2015-12-31 2016-06-08 东北电力大学 Method for enabling thermoelectric unit to participate in system peak-load regulation scheduling by using heat supply time lag
CN105805822A (en) * 2016-03-24 2016-07-27 常州英集动力科技有限公司 Heat supply energy saving control method and system based on neural network prediction
CN105913151A (en) * 2016-04-12 2016-08-31 河海大学常州校区 Photovoltaic power station power generation amount predication method based on adaptive mutation particle swarm and BP network
CN107120721A (en) * 2017-05-25 2017-09-01 河北健特建筑安装工程有限公司 A kind of central heating dynamic gas candidate compensation method
CN107704875A (en) * 2017-09-30 2018-02-16 山东建筑大学 Based on the building load Forecasting Methodology and device for improving IHCMAC neutral nets
CN109253494A (en) * 2018-09-05 2019-01-22 东北大学 A kind of electric heat-storage device control system and method based on heat load prediction

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
文充: "满足舒适要求的空调系统需求相应及错峰运行策略研究", 中国硕士学位论文数据库 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112083746A (en) * 2020-09-25 2020-12-15 陕西科技大学 Intelligent power grid system
CN112083746B (en) * 2020-09-25 2022-01-28 陕西科技大学 Intelligent power grid system
CN117040029A (en) * 2023-10-08 2023-11-10 南方电网数字电网研究院有限公司 Power distribution network power dispatching method, device, computer equipment and storage medium
CN117040029B (en) * 2023-10-08 2024-03-26 南方电网数字电网研究院有限公司 Power distribution network power dispatching method, device, computer equipment and storage medium

Similar Documents

Publication Publication Date Title
Korkas et al. Intelligent energy and thermal comfort management in grid-connected microgrids with heterogeneous occupancy schedule
Tran et al. Nature-inspired metaheuristic ensemble model for forecasting energy consumption in residential buildings
Mpelogianni et al. Re-approaching fuzzy cognitive maps to increase the knowledge of a system
Dombaycı The prediction of heating energy consumption in a model house by using artificial neural networks in Denizli–Turkey
CN109840154B (en) Task dependency-based computing migration method in mobile cloud environment
Jasmin et al. Reinforcement learning approaches to economic dispatch problem
Ellis et al. An encoder–decoder LSTM-based EMPC framework applied to a building HVAC system
Dash et al. Indian summer monsoon rainfall prediction: a comparison of iterative and non-iterative approaches
Liu et al. Evaluation of reinforcement learning for optimal control of building active and passive thermal storage inventory
Ghadimi et al. SqueezeNet for the forecasting of the energy demand using a combined version of the sewing training-based optimization algorithm
Jin et al. User-preference-driven model predictive control of residential building loads and battery storage for demand response
Han et al. Evolutionary game based demand response bidding strategy for end-users using Q-learning and compound differential evolution
CN110991749A (en) Heat supply load prediction method and device
Albouys-Perrois et al. Multi-agent simulation of collective self-consumption: Impacts of storage systems and large-scale energy exchanges
CN116345578A (en) Micro-grid operation optimization scheduling method based on depth deterministic strategy gradient
Gao et al. A multi-objective service composition method considering the interests of tri-stakeholders in cloud manufacturing based on an enhanced jellyfish search optimizer
Mason et al. Building hvac control via neural networks and natural evolution strategies
CN117543537A (en) Agent electricity purchasing user electric quantity prediction method, device and storage medium
CN109426901A (en) Long-term power consumption prediction method and device in one kind
Fadare et al. Modeling of solar energy potential in Africa using an artificial neural network
Wang et al. Multi-agent simulation for strategic bidding in electricity markets using reinforcement learning
CN115705608A (en) Virtual power plant load sensing method and device
Qiu Research on Hierarchical Cooperative Algorithm Based on Genetic Algorithm and Particle Swarm Optimization
CN116739306B (en) Heat pump load flexibility quantification method, system and equipment
Liu et al. Distributed optimal dispatch method for smart community demand response based on machine learning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination